INDEX

Explanations

programming-related syntax and structure elements in code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Franklin

-0.15

Mer

-0.14

ander

-0.14

 Johnson

-0.14

 Mack

-0.14

 Sloan

-0.14

logen

-0.14

allery

-0.14

Mac

-0.14

Tun

-0.13

POSITIVE LOGITS

Ø§Ø¨Ø¹

0.15

adia

0.14

oka

0.14

ars

0.14

 Ð°Ð¼

0.14

 poil

0.14

 ÎĳÎ³

0.14

ARCHAR

0.13

PERTIES

0.13

Activations Density 0.088%

programming-related syntax and structure elements in code

No Comments

No Known Activations